Category
AI
Agents that research and update records, voice agents, assistants that answer from a company's own documents, MCP servers, and how to pick between models like GPT-6 and Claude. How we build them, and where the models still fall short.
26 posts
Databricks Lakebase: managed Postgres next to your lakehouse
What Databricks Lakebase is, how branching, point-in-time restore and synced tables work, who uses it, and when to keep your existing Postgres.
Ivan VydrinReadBC29 retained DEV extensions: VS Code apps survive updates
Business Central 2026 wave 2 keeps DEV extensions installed through an environment update. What changes for sandboxes, UAT and your release process.
Preetham ReddyReadLakebase database branching: a database per coding agent
Databricks Lakebase branches a Postgres database in under a second. Here is how that gives every coding agent and every PR its own isolated database.
Ivan VydrinReadVoice agents on Databricks for auto refinance
How a compliant outbound voice agent for auto refinance is built on Databricks. Consent gating, feature lookups, the agent runtime and what to measure.
Preetham ReddyReadGPT-6: choosing Astra, Sol or Luna and setting effort
How the GPT-6 family splits by cost and reasoning effort, the API rules that changed, what it costs per million tokens, and how to run it on Databricks.
Preetham ReddyReadMeta's ads MCP server on Databricks: what it changes
Meta's ads MCP server is in Databricks Marketplace. What it lets an agent do, how Unity Gateway and Meta rules fence it, and where it does not fit.
Preetham ReddyReadBusiness Central MCP server: query data with no API page
Business Central 29.0 lets agents define, validate and run data queries against tables with no API page. What it does, how to enable it, where it stops.
Preetham ReddyReadUnity Catalog for AI agents in practice: four FHIR scenarios
Agent identity decides what your row filters do. Four scenarios from a FHIR lakehouse on Databricks, with the performance tradeoffs of each.
Sushruth AeluguriReadDecision models in auto refinance: where Jev and Clef fit
How an auto refinance shop can use decision models like Jev and Clef on Databricks to cut underwriter kickbacks before submission.
Preetham ReddyReadAn AI governance framework is four answers you can query
The EU moved its high-risk AI deadline to December 2027. What NIST AI RMF, ISO 42001 and the EU AI Act ask, mapped to controls you can run on Databricks.
Preetham ReddyReadPaying frontier prices to rename a variable
Smart routing in Unity AI Gateway labels a coding task before picking a model. The cost headline is fine. The traces are the part worth reading.
Preetham ReddyReadFinance said ninety days. Operations said open account.
Genie fails when two teams mean different things by the same word. Genie Accuracy hardens the semantic layer. TechFabric Experiments keeps the suite running.
Andrew RipleyReadNobody could tell whether the agent was any good
A team shipped an agent in nine days and argued for two months about whether its answers were right. Write down what a good answer is first.
Preetham ReddyReadDriving Real-World Value with Intelligent Business Intelligence, BI in the era of AI
Databricks AI/BI in practice. Conversational analytics, semantic understanding, and dashboards people actually open.
Preetham ReddyReadFrom Data Warehouses to Data Intelligence: Why Your Next Platform Choice Will Define the Next Decade
Transform your data strategy: From warehouses to AI-powered intelligence platforms. Discover why your platform choice defines the next decade.
Preetham ReddyReadRethink AI: Building a Horizontal Layer for Enterprise-Wide Transformation
Treating AI as a horizontal layer across the business rather than a single-app use case, and what that changes about operations and efficiency.
John BellaudReadIntroducing Azure AI Foundry: A CTO's Guide to Starting and Scaling AI
A CTO's guide to Azure AI Foundry. Pre-trained models, fine-tuning them for your business, and deploying AI securely once it works.
John BellaudReadAI at Scale: Managing Cloud Multi-Tenant AI Infrastructure with Temporal
Scaling, cost and security in a multi-tenant AI application. How TechFabric uses Temporal to orchestrate the infrastructure workflows underneath.
Sergey UstimenkoReadDurable RAG with Temporal and Chainlit
Calling different tools from RAG pipeline can be difficult. This blog post describes how to use temporal for durable execution of RAG tools in Chainlit.
Sergey UstimenkoReadHow We Created A Multi-Tenant, Multi-Cloud, & Multi-Model AI Platform with Temporal, Fiber Copilot
How we built Fiber Copilot, a multi-tenant, multi-cloud and multi-model AI Ops platform for standing up chatbots and copilots quickly.
Preetham ReddyReadWhat Every CTO Needs To Know About Databricks
A CTO's guide to Databricks and what it does with big data. Learn essential strategies to maximize your data potential and drive innovation.
John BellaudReadWhy business can't afford to ignore generative AI: 10 benefits that matter
Ten reasons enterprises adopt generative AI, starting with automating work, improving decisions and producing ideas a team would not have reached.
John BellaudReadBreaking Down Silos: Integrating AI Across Business Functions
What happens when AI runs across business functions rather than inside one. Cases from Amazon and KLM, and the obstacles both had to get past.
Leo OliemansReadIndustry Turning Point: Large Language Models (LLMs)
What large language models are, how they understand and generate text, and what they change about the way people reach information at work.
John BellaudReadMastering the Art of Prompt Engineering for Generative AI
Prompt engineering is writing precise instructions and then iterating on what comes back. How to get accurate, original output from a generative model.
Leo OliemansReadThe Power of Data, AI and Digital Transformation
Digital work shortens the road to a product launch. An agile MVP gets something in front of customers sooner and reaches more of them.
Leo OliemansRead